Systems and methods by a telematics server are provided. The method includes receiving, over a network, training data including model input data and a known output label corresponding to the model input data from a first device, training a centralized machine-learning model using the training data, determining, by the centralized machine-learning model, an output label prediction certainty based on the model input data, determining an increase in the output label prediction certainty over a prior predicted output label certainty of the centralized machine-learning model, and sending, over the network, a machine-learning model update to a second device in response to determining that the increase in the output label prediction certainty is greater than an output label prediction increase threshold.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The method of claim 1, wherein determining the increase in the output label prediction certainty over a prior output label certainty comprises comparing the output label prediction certainty with the output label prediction certainty of a prior machine-learning model update.
3. The method of claim 1, wherein the output label prediction increase threshold comprises a percentage increase in the output label prediction certainty.
4. The method of claim 1, wherein the model input data comprises at least one image of a vehicle's dashboard and the known output label comprises a vehicle parameter corresponding to a gauge on the vehicle's dashboard.
5. The method of claim 1, wherein the model input data comprises at least one image of a vehicle's driver and the known output label comprises a vehicle parameter indicating whether a driver seatbelt of a vehicle is fastened.
6. The method of claim 1, wherein sending the machine-learning model update is further done periodically.
7. The method of claim 1, wherein sending the machine-learning model update is further done in response to receiving, from the second I/O Expansion Adapter, a machine-learning model update request.
8. The method of claim 1, wherein the I/O expansion data comprises raw data received from the second I/O expander.
10. The telematic system of claim 9, wherein the telematics server determines an increase in the output label prediction certainty over a prior predicted output label certainty of the centralized machine-learning model by comparing the output label prediction certainty with the output label prediction certainty of a prior machine-learning model update.
11. The telematics system of claim 9, wherein the output label prediction increase threshold comprises a percentage increase in the output label prediction certainty.
12. The telematics system of claim 9, wherein the I/O expansion data comprises raw data received from the second I/O expander.
13. The telematics system of claim 9, wherein the model input data comprises at least one image of a vehicle's dashboard and the known output label comprises a vehicle parameter corresponding to a gauge on the vehicle's dashboard.
14. The telematics system of claim 9, the model input data comprises at least one image of a vehicle's driver and the known output label comprises a vehicle parameter indicating whether a driver seatbelt of a vehicle is fastened.
15. The telematics system of claim 9, wherein the telematics server sends, over the network, the machine-learning model update to the second I/O expansion adapter periodically.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
April 6, 2022
July 4, 2023
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.